PersonNet: Person Re-identification with Deep Convolutional Neural Networks

By Lin Wu, Chunhua Shen, Anton van den Hengel. 2016

233 citations recorded by the source corpus.

In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification. The network takes a pair of raw RGB images as input, and outputs a similarity value indicating whether the two input images depict the same person. A layer of computing neighborhood range differences across two input images is employed to capture local relationship between patches. This operation is to seek a robust feature from input images. By increasing the depth to 10 weight layers and using very small (3$\times$3) convolution filters, our architecture achieves a remarkable improvement on the prior-art configurations. Meanwhile, an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into our architecture, which is beneficial to deep nets. Our method consistently outperforms state-of-the-art on two large datasets (CUHK03 and Market-1501), and a medium-sized data set (CUHK01).

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Yi Yang
2. Liang Zheng
3. Zhedong Zheng
4. Qi Tian
5. Shiliang Zhang
6. Wanli Ouyang
7. Tao A. Xiang
8. Wen Gao

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Luc Van Gool
3. Xiaogang Wang
4. Liang Zheng
5. Dacheng Tao
6. Qi Tian
7. Ling Shao
8. Tao A. Xiang

Citations in the corpus

• Faceless Person Recognition: Privacy Implications in Social Media (2016, background): “When only one training sample is available and many test images (typical for face recognition and surveillance scenarios [10, 12, 32]), the problem is usually named “re-identification”, and it becomes akin to metric learning or ranking problems.”
• Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification (2017, unknown): “Recently, CNN-based features [2,21,22,27] have also achieved great progress on person ReID.”
• Attention-Aware Compositional Network for Person Re-identification (2018, background): “The first category mainly includes the traditional feature descriptors [53, 52, 51, 27, 7, 31, 35] and deep learning features [43, 41, 42, 12, 25, 40].”
• Camera Style Adaptation for Person Re-identification (2017, background): “Many deep learning methods [38, 34, 33, 3, 24] have been proposed in person re-ID.”
• Pose-Driven Deep Convolutional Model for Person Re-identification (2017, methodology): “Compared works based on deep learning are PersonNet [52], Gate SCNN [46], LSTM S-CNN [47], PIE [62] and Spindle [16].”
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis (2017, methodology): “The success of deep learning in image clas-sification inspired lots of studies on person ReID [5, 16, 30, 29, 26, 23, 25, 15, 31].”
• A Discriminatively Learned CNN Embedding for Person Reidentification (2016, background): “Recently, the CNN has shown potential for learning state-of-the-art feature embeddings or deep metrics [5, 18, 38, 43, 44, 47, 56].”
• Person Re-identification: Past, Present and Future (2016, methodology): “Wu et al. [70] deepen the networks using convolutional filters of smaller sizes, called “PersonNet”.”
• Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification (2017, methodology): “Market1501: For the Market1501 dataset, several state-of-the-art methods are compared, including Bag of Words (BOW) [53], Weighted Approximate Rank Component Analysis (WARCA) [15], Discriminative Null Space (DNS) [47], Spatially Constrained Similarity function on Polynomial feature map (SCSP) [2], a”
• Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion (2017, methodology): “The proposed Spindle Net is compared with several state-of-the-art ReID approaches in recent two years, including the metric learning method WARCA-χ2 [11], the null space semi-supervised learning method NFST [32], the deep neural network PersonNet [28], the Siamese CNN with learnable gate S-CNN [25]”
• Deep Representation Learning With Part Loss for Person Re-Identification (2017, background): “[35] propose a”
• Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “To capture the fine-grained cues in global feature learning, Wu et al. [73] design a “PersonNet” using small-sized convolutional filters to capture the fine-grained cues in the person image.”